A Long Skip Connection for Enhanced Color Selectivity in CNN Architectures

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired by the visual cortex, are characterized by their hierarchical learning structure which appears to gradually transform the repres...

Full description

Bibliographic Details
Main Authors: Oscar Sanchez-Cesteros, Mariano Rincon, Margarita Bachiller, Sonia Valladares-Rodriguez
Format: Article
Language:English
Published: MDPI AG 2023-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/17/7582